linux-kernel - Re: [PATCH v2] x86/mce: work around an erratum on fast string copy instructions.

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <Yg/UUHuVvd9AOJ94@zn.tnic>
Date:   Fri, 18 Feb 2022 18:16:00 +0100
From:   Borislav Petkov <bp@...en8.de>
To:     Jue Wang <juew@...gle.com>
Cc:     Tony Luck <tony.luck@...el.com>, x86@...nel.org,
        linux-kernel@...r.kernel.org, patches@...ts.linux.dev
Subject: Re: [PATCH v2] x86/mce: work around an erratum on fast string copy
 instructions.

On Fri, Feb 18, 2022 at 08:21:36AM -0800, Jue Wang wrote:
> My concern was that here returns 0 instead the value read from the msr.

You'd walk into that code only if you're doing MCE injections. In that
case, it won't read or write MSR_IA32_MISC_ENABLE because the injection
code writes into the injection mce struct only.

So it won't disable fast strings when you manage to inject the exact
error type which triggers this erratum.

I think that's actually a good thing - you don't want to disable fast
strings just because you injected a particular MCE type.

-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette